Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    certain symbols, operators, and math-related terms in program code

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bra
    -0.57
    SequentialGroup
    -0.53
    TabStop
    -0.52
    司
    -0.52
    woj
    -0.50
    bra
    -0.49
     bra
    -0.49
    Bra
    -0.48
    tuj
    -0.48
    wo
    -0.48
    POSITIVE LOGITS
     itſelf
    0.79
     pleaſure
    0.77
     Theſe
    0.75
     myſelf
    0.75
     ſmall
    0.74
     Efq
    0.74
     Jefus
    0.73
    Personensuche
    0.72
     ſhe
    0.71
    ^(@)
    0.71
    Act Density 0.680%

    No Known Activations